Gen-Verse

OpenClaw-RL: Train any agent simply by talking

MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion, mixed-CoT, unified RL)

[ICML 2026 Spotlight] Latent Collaboration in Multi-Agent Systems

RSI-Anything: Unlocking Recursive Self-Improvement with World Models

RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios

[NeurIPS 2025 Spotlight] LLM post-training suite — featuring ReasonFlux, ReasonFlux-PRM, and ReasonFlux-Coder.

[ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, powering the SOTA TraDo series.

ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents

JEPA-Anything: Learning Predictive Models across Different Worlds

Recursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses

[NeurIPS 2025 Spotlight] Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning

DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses

WideRange4D: Enabling High-Quality 4D Reconstruction with Wide-Range Movements and Scenes

ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization

[NeurIPS 2025] HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation

Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening

[NeurIPS 2026] GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators

[ICCV 2025] Preacher: Paper-to-Video Agentic System